Papers › Near-Linear Time Projection onto the ℓ_(1,∞) Ball; Application to Sparse Autoencoders
Near-Linear Time Projection onto the ℓ_(1,∞) Ball; Application to Sparse Autoencoders
Guillaume Perez, Laurent Condat, Michel Barlaud
Looking for sparsity is nowadays crucial to speed up the training of large-scale neural networks. Projections onto the ℓ_(1,2) and ℓ_(1,∞) are among the most efficient techniques to sparsify and reduce the overall cost of neural networks. In this paper, we introduce a new projection algorithm for the ℓ_(1,∞) norm ball. The worst-case time complexity of this algorithm is 𝒪(nm+Jlog(nm)) for a matrix in ℝ^(n×m). J is a term that tends to 0 when the sparsity is high, and to nm when the sparsity is low. Its implementation is easy and it is guaranteed to converge to the exact solution in a finite time. Moreover, we propose to incorporate the ℓ_(1,∞) ball projection while training an autoencoder to enforce feature selection and sparsity of the weights. Sparsification appears in the encoder to primarily do feature selection due to our application in biology, where only a very small part (<2%) of the data is relevant. We show that both in the biological case and in the general case of sparsity that our method is the fastest.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections